{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:00:00Z","timestamp":1784822400647,"version":"3.55.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"S1","license":[{"start":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T00:00:00Z","timestamp":1713139200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T00:00:00Z","timestamp":1713139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11760-024-03176-3","type":"journal-article","created":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T08:01:56Z","timestamp":1713168116000},"page":"585-598","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Small target detection in drone aerial images based on feature fusion"],"prefix":"10.1007","volume":"18","author":[{"given":"Aiming","family":"Mu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huajun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,4,15]]},"reference":[{"key":"3176_CR1","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014). https:\/\/doi.org\/10.48550\/arXiv.1311.2524","DOI":"10.48550\/arXiv.1311.2524"},{"key":"3176_CR2","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"3176_CR3","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3176_CR4","doi-asserted-by":"publisher","unstructured":"Liu, W., Anguelov, D., Erhan, D., et al.: SSD: single shot MultiBox detector. In: Computer vision-ECCV, pp. 21\u201337 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3176_CR5","doi-asserted-by":"publisher","unstructured":"Redmo, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"3176_CR6","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"3176_CR7","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"3176_CR8","unstructured":"Bochkovskiy, A., Wang, C.Y., et al.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"3176_CR9","unstructured":"Glenn, J.: YOLOv5 release v6.0. https:\/\/github.com\/ultralytics\/yolov5\/releases\/tag\/v6.0. Accessed 26 June 2023 (2022)"},{"key":"3176_CR10","unstructured":"C, Li., L, Li., H, Jiang., et al.: YOLOv6: a single-stage object detection framework for industrial applications (2022). arXiv preprint arXiv:2209.02976"},{"key":"3176_CR11","doi-asserted-by":"publisher","unstructured":"Wang, C., Bochkovskiy, A., et al.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u20137475 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00721","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"3176_CR12","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume":"2014","author":"T Lin","year":"2014","unstructured":"Lin, T., Maire, M., Belongie, S., et al.: Microsoft COCO: common objects in context. Comput. Vis. ECCV 2014, 740\u2013755 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","journal-title":"Comput. Vis. ECCV"},{"issue":"19","key":"3176_CR13","doi-asserted-by":"publisher","first-page":"3140","DOI":"10.3390\/rs12193140","volume":"12","author":"R Zhang","year":"2020","unstructured":"Zhang, R., Shao, Z., Huang, X., et al.: Object detection in UAV images via global density fused convolutional network. Remote Sens. 12(19), 3140 (2020). https:\/\/doi.org\/10.3390\/rs12193140","journal-title":"Remote Sens."},{"key":"3176_CR14","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint (2015). arXiv:1511.07122"},{"key":"3176_CR15","doi-asserted-by":"publisher","unstructured":"Liu, S., Zha, J., Sun, J. l.: EdgeYOLO: an edge-real-time object detector. In: 2023 42nd Chinese Control Conference, pp. 7507\u20137512 (2023). https:\/\/doi.org\/10.23919\/CCC58697.2023.10239786","DOI":"10.23919\/CCC58697.2023.10239786"},{"issue":"14","key":"3176_CR16","doi-asserted-by":"publisher","first-page":"3468","DOI":"10.3390\/rs15143468","volume":"15","author":"L Zhou","year":"2023","unstructured":"Zhou, L., Liu, Z., Zhao, H., et al.: A multi-scale object detector based on coordinate and global information aggregation for UAV aerial images. Remote Sens. 15(14), 3468 (2023). https:\/\/doi.org\/10.3390\/rs15143468","journal-title":"Remote Sens."},{"key":"3176_CR17","doi-asserted-by":"publisher","unstructured":"Yu, W., Yang, T., Chen, C.: Towards resolving the challenge of long-tail distribution in UAV images for object detection. In: 2021 IEEE Winter Conference on Applications of Computer Vision, pp. 3257\u20133266 (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00330","DOI":"10.1109\/WACV48630.2021.00330"},{"key":"3176_CR18","doi-asserted-by":"publisher","unstructured":"Tan, M., Pang, R., Le, Q., et al.: EfficientDet: scalable and efficient object detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10778\u201310787. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"3176_CR19","doi-asserted-by":"publisher","unstructured":"Liu, S., Huang, D., Wang, Y.: Receptive field block net for accurate and fast object detection. In: Proceedings of the European Conference on Computer Vision, pp. 385\u2013400 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_24","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"3176_CR20","doi-asserted-by":"publisher","unstructured":"Song, G., Liu, Y., Wang, X.: Revisiting the sibling head in object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11560\u201311569 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01158","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"3176_CR21","unstructured":"Ge, Z., Liu, S., Wang, F., et al.: YOLOX: Exceeding yolo series in 2021 (2021). arXiv preprint arXiv:2107.08430"},{"key":"3176_CR22","doi-asserted-by":"publisher","unstructured":"Zhu, X., Lyu, S., Wang, X., et al.: TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2778\u20132788 (2021). https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00312","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"3176_CR23","doi-asserted-by":"publisher","unstructured":"Huang, R., Pedoeem, J., Chen, C., et al.: YOLO-LITE: a real-time object detection algorithm optimized for non-GPU computers. In: 2018 IEEE International Conference on Big Data, pp. 2503\u20132510 (2018). https:\/\/doi.org\/10.1109\/BigData.2018.8621865","DOI":"10.1109\/BigData.2018.8621865"},{"key":"3176_CR24","doi-asserted-by":"publisher","unstructured":"Lin, T., Doll\u00e1ir, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 936\u2013944 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"3176_CR25","doi-asserted-by":"publisher","unstructured":"Liu, S., Qi, L., Qin, H. et al.: Path aggregation network for instance segmentation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00913","DOI":"10.1109\/CVPR.2018.00913"},{"key":"3176_CR26","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3176_CR27","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3176_CR28","doi-asserted-by":"publisher","unstructured":"Yu, J., Jiang, Y., Wang, Z., et al.: UnitBox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 516\u2013520. (2016) https:\/\/doi.org\/10.1145\/2964284.2967274","DOI":"10.1145\/2964284.2967274"},{"key":"3176_CR29","doi-asserted-by":"publisher","unstructured":"Zheng, Z., Wang, P., Liu, W., et al.: Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12993\u201313000 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6999","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"3176_CR30","doi-asserted-by":"publisher","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., et al.: Generalized Intersection over union: a metric and a loss for bounding box regression. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00075","DOI":"10.1109\/CVPR.2019.00075"},{"key":"3176_CR31","doi-asserted-by":"publisher","unstructured":"Zhang, H., Wang, Y., Dayoub, F.: VarifocalNet: an IoU-aware dense object detector. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8510\u20138519 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00841","DOI":"10.1109\/CVPR46437.2021.00841"},{"issue":"11","key":"3176_CR32","doi-asserted-by":"publisher","first-page":"1783","DOI":"10.3390\/jmse10111783","volume":"10","author":"Z Shao","year":"2022","unstructured":"Shao, Z., Lyu, H., Yin, Y., Cheng, T., et al.: Multi-scale object detection model for autonomous ship navigation in maritime environment. J. Mar. Sci. Eng. 10(11), 1783 (2022). https:\/\/doi.org\/10.3390\/jmse10111783","journal-title":"J. Mar. Sci. Eng."},{"key":"3176_CR33","doi-asserted-by":"publisher","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456 (2015). https:\/\/doi.org\/10.5555\/3045118.3045167","DOI":"10.5555\/3045118.3045167"},{"key":"3176_CR34","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3\u201311 (2018). https:\/\/doi.org\/10.1016\/j.neunet.2017.12.012","journal-title":"Neural Netw."},{"key":"3176_CR35","doi-asserted-by":"publisher","unstructured":"Srinivas, A., Lin, T., Parmar, N. et al.: Bottleneck transformers for visual recognition. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16514\u201316524 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01625","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"3176_CR36","doi-asserted-by":"publisher","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3176_CR37","unstructured":"Xavier, G., Antoine, B., Yoshua, B.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, vol. 15, pp. 315\u2013323 (2011)"},{"key":"3176_CR38","doi-asserted-by":"publisher","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1800\u20131807 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"3176_CR39","doi-asserted-by":"publisher","unstructured":"Du, D., Zhu, P. et al.: (2019) VisDrone-DET2019: the vision meets drone object detection in image challenge results. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop, pp. 213\u2013226. https:\/\/doi.org\/10.1109\/ICCVW.2019.00030","DOI":"10.1109\/ICCVW.2019.00030"},{"issue":"8","key":"3176_CR40","doi-asserted-by":"publisher","first-page":"1850","DOI":"10.3390\/rs14081850","volume":"14","author":"H Guo","year":"2022","unstructured":"Guo, H., Bai, H., Yuan, Y., et al.: Fully deformable convolutional network for ship detection in remote sensing imagery. Remote Sens. 14(8), 1850 (2022). https:\/\/doi.org\/10.3390\/rs14081850","journal-title":"Remote Sens."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03176-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03176-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03176-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T12:21:52Z","timestamp":1719318112000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03176-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,15]]},"references-count":40,"journal-issue":{"issue":"S1","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["3176"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03176-3","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,15]]},"assertion":[{"value":"2 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study does not have conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}